suhwan3/mini-lm-finetuned-step1

SentenceTransformer based on sentence-transformers/all-MiniLM-L12-v2

This is a sentence-transformers model finetuned from sentence-transformers/all-MiniLM-L12-v2 on the pre-finetune dataset. It maps sentences & paragraphs to a 384-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

• Model Type: Sentence Transformer
• Base model: sentence-transformers/all-MiniLM-L12-v2
• Maximum Sequence Length: 128 tokens
• Output Dimensionality: 384 dimensions
• Similarity Function: Cosine Similarity
• Training Dataset:
  • pre-finetune

Model Sources

• Documentation: Sentence Transformers Documentation
• Repository: Sentence Transformers on GitHub
• Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
  (2): Normalize()
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("sentence_transformers_model_id")
# Run inference
sentences = [
    "The SPDR S&P Health Care Services ETF (XHS) aims to mirror the performance of the S&P Health Care Services Select Industry Index by employing a sampling strategy, investing at least 80% of its assets in the index's securities. This index, part of the S&P Total Market Index, focuses on the U.S. health care services sector, including related industries like medical equipment, pharmaceuticals, and drug retailers. XHS offers unique exposure by equally weighting its holdings, which results in a tilt towards smaller companies and an underweighting of large managed health care firms. The index is rebalanced quarterly, ensuring a dynamic and diversified portfolio.",
    "Castle Biosciences, Inc., a commercial-stage diagnostics company, focuses to provide diagnostic and prognostic testing services for dermatological cancers. Its lead product is DecisionDx-Melanoma, a multi-gene expression profile (GEP) test to identify the risk of metastasis for patients diagnosed with invasive cutaneous melanoma. The company also offers DecisionDx-UM test, a proprietary GEP test that predicts the risk of metastasis for patients with uveal melanoma, a rare eye cancer; DecisionDx-SCC, a proprietary 40-gene expression profile test that uses an individual patient's tumor biology to predict individual risk of squamous cell carcinoma metastasis for patients with one or more risk factors; and DecisionDx DiffDx-Melanoma and myPath Melanoma, a proprietary GEP test to diagnose suspicious pigmented lesions. It offers test services through physicians and their patients. The company was founded in 2007 and is headquartered in Friendswood, Texas.",
    'Invesco Senior Income Trust is a closed ended fixed income mutual fund launched by Invesco Ltd. It is co-managed by Invesco Advisers, Inc., Invesco Asset Management Deutschland GmbH, Invesco Asset Management Limited, Invesco Asset Management (Japan) Limited, Invesco Australia Limited, Invesco Hong Kong Limited, Invesco Senior Secured Management, Inc., and Invesco Canada Ltd. The fund invests in the fixed income markets of the United States. It primarily invests in a portfolio of interests in floating or variable rate senior loans to corporations, partnerships, and other entities which operate in a variety of industries and geographical regions. The fund typically employs fundamental analysis with a bottom up stock picking approach to create its portfolio. It benchmarks the performance of its portfolio against the Credit Suisse Leveraged Loan Index. The fund was formerly known as Invesco Van Kampen Senior Income Trust and Van Kampen Senior Income Trust. Invesco Senior Income Trust was formed on June 23, 1998 and is domiciled in the United States.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 384]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Training Details

Training Dataset

pre-finetune

• Dataset: pre-finetune at 5e8c10c
• Size: 14,388 training samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 120 tokens mean: 127.97 tokens max: 128 tokens	min: 21 tokens mean: 122.36 tokens max: 128 tokens

• Samples:

  anchor	positive
  The ETF Series Solutions AAM Transf (TRFM) employs a passive management strategy to track the Pence Transformers Index, focusing on U.S.-listed equities, including ADRs, that are set to benefit from significant disruptions in consumer behavior and technological innovation. The index is rules-based and modified equal-weighted, emphasizing companies with substantial R&D spending. It targets sectors like autonomous driving, electric vehicles, the digital economy, 5G, low-carbon technologies, and renewable energy. Eligible companies must have a market cap of at least $2 billion and meet analyst rating criteria. The portfolio is tiered by market cap and domicile, with 75% allocated to U.S. companies, and is reconstituted quarterly.	Nova Ltd. designs, develops, produces, and sells process control systems used in the manufacture of semiconductors in Israel, Taiwan, the United States, China, Korea, and internationally. Its product portfolio includes a set of metrology platforms for dimensional, films, and materials and chemical metrology measurements for process control for various semiconductor manufacturing process steps, including lithography, etch, chemical mechanical planarization, deposition, electrochemical plating, and advanced packaging. The company serves various sectors of the integrated circuit manufacturing industry, including logic, foundries, and memory manufacturers, as well as process equipment manufacturers. Nova Ltd. was formerly known as Nova Measuring Instruments Ltd. and changed its name to Nova Ltd. in July 2021. The company was incorporated in 1993 and is headquartered in Rehovot, Israel.
  The U.S. Global Jets ETF (JETS) employs a passive management strategy to track the U.S. Global Jets Index, focusing on U.S. and international airline companies, including passenger airlines, aircraft manufacturers, and airport services. The fund is non-diversified and uses a tiered weighting scheme primarily based on market cap and passenger load. Approximately 70% of its portfolio is allocated to large-cap U.S. passenger airlines, with the top four companies receiving 10% each. The next five largest U.S. or Canadian airlines receive 4% each, while other companies meeting trading and liquidity criteria are weighted based on fundamental factors like cash flow return on capital and sales growth.	United Airlines Holdings, Inc., through its subsidiaries, provides air transportation services in North America, Asia, Europe, Africa, the Pacific, the Middle East, and Latin America. The company transports people and cargo through its mainline and regional fleets. It also offers catering, ground handling, training, and maintenance services for third parties. The company was formerly known as United Continental Holdings, Inc. and changed its name to United Airlines Holdings, Inc. in June 2019. United Airlines Holdings, Inc. was incorporated in 1968 and is headquartered in Chicago, Illinois.
  The SPDR S&P Bank ETF (KBE) aims to deliver investment results that correspond to the total return performance of the S&P Banks Select Industry Index, which is part of the S&P Total Market Index tracking the broad U.S. equity market. KBE invests at least 80% of its total assets in securities within this index, focusing on the bank segment, including sub-industries like Asset Management & Custody Banks, Diversified Banks, Regional Banks, Other Diversified Financial Services, and Thrifts & Mortgage Finance. The fund employs an equal-weighted strategy, rebalancing quarterly to ensure equal emphasis on both large and small banking firms, thus providing diversified exposure across the banking sector. Additionally, KBE may hold equity securities outside the index, cash, and money market instruments to maintain liquidity and flexibility.	MGIC Investment Corporation, through its subsidiaries, provides private mortgage insurance, other mortgage credit risk management solutions, and ancillary services to lenders and government sponsored entities in the United States, Puerto Rico, and Guam. The company offers primary mortgage insurance that provides mortgage default protection on individual loans, as well as covers unpaid loan principal, delinquent interest, and various expenses associated with the default and subsequent foreclosure. It also provides contract underwriting services, as well as reinsurance. The company serves originators of residential mortgage loans, including savings institutions, commercial banks, mortgage brokers, credit unions, mortgage bankers, and other lenders. MGIC Investment Corporation was founded in 1957 and is headquartered in Milwaukee, Wisconsin.

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Evaluation Dataset

pre-finetune

• Dataset: pre-finetune at 5e8c10c
• Size: 3,597 evaluation samples
• Columns: anchor and positive
• Approximate statistics based on the first 1000 samples:

  	anchor	positive
  type	string	string
  details	min: 120 tokens mean: 127.99 tokens max: 128 tokens	min: 22 tokens mean: 122.47 tokens max: 128 tokens

• Samples:

  anchor	positive
  The Goldman Sachs Future Health Care ETF (GDOC) seeks long-term capital growth by investing at least 80% of its net assets in equity investments of U.S. and non-U.S. healthcare companies. This actively managed, non-diversified fund targets innovators and disruptors in the healthcare sector, focusing on key themes such as genomics, precision medicine, technology-enabled procedures, and digital healthcare. GDOC may invest in companies of any market capitalization and may use derivatives like futures and options to achieve its investment goals. The fund's adviser employs a fundamental investment process that may integrate ESG factors, utilizing company disclosures, third-party research, and engagement to inform decisions. The fund's thematic allocations can vary over time at the adviser's discretion.	Insulet Corporation develops, manufactures, and sells insulin delivery systems for people with insulin-dependent diabetes. It offers Omnipod System, a self-adhesive disposable tubeless Omnipod device that is worn on the body for up to three days at a time, as well as its wireless companion, the handheld personal diabetes manager. The company sells its products primarily through independent distributors and pharmacy channels, as well as directly in the United States, Canada, Europe, the Middle East, and Australia. Insulet Corporation was incorporated in 2000 and is headquartered in Acton, Massachusetts.
  The J.P. Morgan Exchange-Traded Fund (JPRE) aims to provide high total investment return through capital appreciation and current income by investing at least 80% of its net assets in equity securities of real estate investment trusts (REITs), including both equity and mortgage REITs across various market capitalizations. As an actively managed, non-diversified fund, JPRE focuses on U.S. REITs with strong financials, operating revenues, and growth potential. The fund employs a disciplined investment process, evaluating securities based on their ability to generate long-term earnings and growth, while also considering ESG factors. On May 20, 2022, JPRE acquired the assets and liabilities of the JPMorgan Realty Income Fund, which had $2.2 billion in assets, enhancing its investment strategy and historical performance data.	Extra Space Storage Inc., headquartered in Salt Lake City, Utah, is a self-administered and self-managed REIT and a member of the S&P 500. As of September 30, 2020, the Company owned and/or operated 1,906 self-storage stores in 40 states, Washington, D.C. and Puerto Rico. The Company's stores comprise approximately 1.4 million units and approximately 147.5 million square feet of rentable space. The Company offers customers a wide selection of conveniently located and secure storage units across the country, including boat storage, RV storage and business storage. The Company is the second largest owner and/or operator of self-storage stores in the United States and is the largest self-storage management company in the United States.
  The First Trust Indxx Metaverse ETF (ARVR) aims to replicate the performance of the Indxx Metaverse Index, investing at least 80% of its net assets in securities within the index. This non-diversified fund targets companies globally that are integral to the Metaverse, focusing on those generating at least 50% of their revenue from five key sub-themes: IP & Contents, Platforms, Payment, Optics & Display, and Semiconductor, Hardware & 5G. The portfolio, comprising 50 companies selected by market-cap, is weighted using revenue thresholds, favoring firms with higher Metaverse-related revenue. Stocks are equally weighted, capped at 2%, and adjusted for market-cap, with the index rebalanced quarterly and reconstituted semi-annually.	Adobe Inc. operates as a diversified software company worldwide. It operates through three segments: Digital Media, Digital Experience, and Publishing and Advertising. The Digital Media segment offers products, services, and solutions that enable individuals, teams, and enterprises to create, publish, and promote content; and Document Cloud, a unified cloud-based document services platform. Its flagship product is Creative Cloud, a subscription service that allows members to access its creative products. This segment serves content creators, workers, marketers, educators, enthusiasts, communicators, and consumers. The Digital Experience segment provides an integrated platform and set of applications and services that enable brands and businesses to create, manage, execute, measure, monetize, and optimize customer experiences from analytics to commerce. This segment serves marketers, advertisers, agencies, publishers, merchandisers, merchants, web analysts, data scientists, developers, ...

• Loss: MultipleNegativesRankingLoss with these parameters:

  {
      "scale": 20.0,
      "similarity_fct": "cos_sim"
  }
  

Training Hyperparameters

Non-Default Hyperparameters

• eval_strategy: steps
• num_train_epochs: 10
• warmup_ratio: 0.1
• bf16: True
• dataloader_drop_last: True
• load_best_model_at_end: True
• batch_sampler: no_duplicates

All Hyperparameters

Click to expand

• overwrite_output_dir: False
• do_predict: False
• eval_strategy: steps
• prediction_loss_only: True
• per_device_train_batch_size: 8
• per_device_eval_batch_size: 8
• per_gpu_train_batch_size: None
• per_gpu_eval_batch_size: None
• gradient_accumulation_steps: 1
• eval_accumulation_steps: None
• torch_empty_cache_steps: None
• learning_rate: 5e-05
• weight_decay: 0.0
• adam_beta1: 0.9
• adam_beta2: 0.999
• adam_epsilon: 1e-08
• max_grad_norm: 1.0
• num_train_epochs: 10
• max_steps: -1
• lr_scheduler_type: linear
• lr_scheduler_kwargs: {}
• warmup_ratio: 0.1
• warmup_steps: 0
• log_level: passive
• log_level_replica: warning
• log_on_each_node: True
• logging_nan_inf_filter: True
• save_safetensors: True
• save_on_each_node: False
• save_only_model: False
• restore_callback_states_from_checkpoint: False
• no_cuda: False
• use_cpu: False
• use_mps_device: False
• seed: 42
• data_seed: None
• jit_mode_eval: False
• use_ipex: False
• bf16: True
• fp16: False
• fp16_opt_level: O1
• half_precision_backend: auto
• bf16_full_eval: False
• fp16_full_eval: False
• tf32: None
• local_rank: 0
• ddp_backend: None
• tpu_num_cores: None
• tpu_metrics_debug: False
• debug: []
• dataloader_drop_last: True
• dataloader_num_workers: 0
• dataloader_prefetch_factor: None
• past_index: -1
• disable_tqdm: False
• remove_unused_columns: True
• label_names: None
• load_best_model_at_end: True
• ignore_data_skip: False
• fsdp: []
• fsdp_min_num_params: 0
• fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
• tp_size: 0
• fsdp_transformer_layer_cls_to_wrap: None
• accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
• deepspeed: None
• label_smoothing_factor: 0.0
• optim: adamw_torch
• optim_args: None
• adafactor: False
• group_by_length: False
• length_column_name: length
• ddp_find_unused_parameters: None
• ddp_bucket_cap_mb: None
• ddp_broadcast_buffers: False
• dataloader_pin_memory: True
• dataloader_persistent_workers: False
• skip_memory_metrics: True
• use_legacy_prediction_loop: False
• push_to_hub: False
• resume_from_checkpoint: None
• hub_model_id: None
• hub_strategy: every_save
• hub_private_repo: None
• hub_always_push: False
• gradient_checkpointing: False
• gradient_checkpointing_kwargs: None
• include_inputs_for_metrics: False
• include_for_metrics: []
• eval_do_concat_batches: True
• fp16_backend: auto
• push_to_hub_model_id: None
• push_to_hub_organization: None
• mp_parameters:
• auto_find_batch_size: False
• full_determinism: False
• torchdynamo: None
• ray_scope: last
• ddp_timeout: 1800
• torch_compile: False
• torch_compile_backend: None
• torch_compile_mode: None
• include_tokens_per_second: False
• include_num_input_tokens_seen: False
• neftune_noise_alpha: None
• optim_target_modules: None
• batch_eval_metrics: False
• eval_on_start: False
• use_liger_kernel: False
• eval_use_gather_object: False
• average_tokens_across_devices: False
• prompts: None
• batch_sampler: no_duplicates
• multi_dataset_batch_sampler: proportional

Training Logs

Click to expand

Epoch	Step	Training Loss	Validation Loss
0.0056	10	2.0017	-
0.0111	20	1.7604	-
0.0167	30	1.7855	-
0.0222	40	2.1169	-
0.0278	50	1.7254	-
0.0334	60	1.3081	-
0.0389	70	1.5951	-
0.0445	80	1.4423	-
0.0501	90	1.1902	-
0.0556	100	1.2449	1.2373
0.0612	110	1.3177	-
0.0667	120	1.2411	-
0.0723	130	1.266	-
0.0779	140	1.2949	-
0.0834	150	1.1601	-
0.0890	160	1.2164	-
0.0945	170	0.9354	-
0.1001	180	1.1337	-
0.1057	190	0.8352	-
0.1112	200	1.0118	1.0049
0.1168	210	0.8274	-
0.1224	220	1.1467	-
0.1279	230	1.0113	-
0.1335	240	0.9029	-
0.1390	250	0.7778	-
0.1446	260	0.7863	-
0.1502	270	0.8369	-
0.1557	280	0.8474	-
0.1613	290	0.8498	-
0.1669	300	0.8299	0.8631
0.1724	310	0.9025	-
0.1780	320	0.6665	-
0.1835	330	1.1485	-
0.1891	340	0.8733	-
0.1947	350	0.8992	-
0.2002	360	0.567	-
0.2058	370	0.9371	-
0.2113	380	0.8934	-
0.2169	390	1.0511	-
0.2225	400	0.6262	0.7888
0.2280	410	0.6581	-
0.2336	420	0.7694	-
0.2392	430	0.7046	-
0.2447	440	0.5984	-
0.2503	450	0.7362	-
0.2558	460	0.6819	-
0.2614	470	0.7147	-
0.2670	480	1.2227	-
0.2725	490	0.694	-
0.2781	500	0.7129	0.7650
0.2836	510	0.592	-
0.2892	520	0.7802	-
0.2948	530	0.6695	-
0.3003	540	0.8442	-
0.3059	550	0.9118	-
0.3115	560	0.8278	-
0.3170	570	0.7366	-
0.3226	580	0.889	-
0.3281	590	0.7323	-
0.3337	600	0.5478	0.7326
0.3393	610	0.5562	-
0.3448	620	0.8333	-
0.3504	630	0.6804	-
0.3560	640	0.68	-
0.3615	650	0.6592	-
0.3671	660	0.7572	-
0.3726	670	0.5261	-
0.3782	680	0.6703	-
0.3838	690	0.7719	-
0.3893	700	0.6809	0.7414
0.3949	710	0.8704	-
0.4004	720	0.5926	-
0.4060	730	0.8478	-
0.4116	740	0.6448	-
0.4171	750	0.8352	-
0.4227	760	0.6417	-
0.4283	770	0.6317	-
0.4338	780	0.8715	-
0.4394	790	0.6437	-
0.4449	800	0.5226	0.7210
0.4505	810	0.7438	-
0.4561	820	0.5888	-
0.4616	830	0.6922	-
0.4672	840	0.5851	-
0.4727	850	0.767	-
0.4783	860	0.7227	-
0.4839	870	0.7196	-
0.4894	880	0.5192	-
0.4950	890	0.7199	-
0.5006	900	0.7474	0.6889
0.5061	910	0.8965	-
0.5117	920	0.6767	-
0.5172	930	0.6318	-
0.5228	940	0.6522	-
0.5284	950	0.6574	-
0.5339	960	0.6544	-
0.5395	970	0.7488	-
0.5451	980	0.5972	-
0.5506	990	0.5109	-
0.5562	1000	0.5295	0.7493
0.5617	1010	0.9111	-
0.5673	1020	0.6716	-
0.5729	1030	0.6971	-
0.5784	1040	0.7311	-
0.5840	1050	0.676	-
0.5895	1060	0.6864	-
0.5951	1070	0.885	-
0.6007	1080	0.668	-
0.6062	1090	0.5427	-
0.6118	1100	0.5875	0.7083
0.6174	1110	0.8703	-
0.6229	1120	0.6143	-
0.6285	1130	0.6069	-
0.6340	1140	0.639	-
0.6396	1150	0.8214	-
0.6452	1160	0.638	-
0.6507	1170	0.692	-
0.6563	1180	0.5953	-
0.6618	1190	0.5384	-
0.6674	1200	0.7248	0.7398
0.6730	1210	0.7493	-
0.6785	1220	0.6966	-
0.6841	1230	0.564	-
0.6897	1240	0.6447	-
0.6952	1250	0.4488	-
0.7008	1260	0.7266	-
0.7063	1270	0.847	-
0.7119	1280	0.5734	-
0.7175	1290	0.5047	-
0.7230	1300	0.7196	0.7221
0.7286	1310	0.7561	-
0.7341	1320	0.5301	-
0.7397	1330	0.8898	-
0.7453	1340	0.9251	-
0.7508	1350	0.5438	-
0.7564	1360	0.7402	-
0.7620	1370	0.7043	-
0.7675	1380	0.7119	-
0.7731	1390	0.6493	-
0.7786	1400	0.6253	0.6853
0.7842	1410	0.7815	-
0.7898	1420	0.6936	-
0.7953	1430	0.5198	-
0.8009	1440	0.7672	-
0.8065	1450	0.5436	-
0.8120	1460	0.6117	-
0.8176	1470	0.7137	-
0.8231	1480	0.7257	-
0.8287	1490	0.9861	-
0.8343	1500	0.7558	0.6728
0.8398	1510	0.7658	-
0.8454	1520	0.6785	-
0.8509	1530	0.6592	-
0.8565	1540	0.5787	-
0.8621	1550	0.5519	-
0.8676	1560	0.5911	-
0.8732	1570	0.5285	-
0.8788	1580	0.8498	-
0.8843	1590	0.5782	-
0.8899	1600	0.7702	0.6698
0.8954	1610	0.6775	-
0.9010	1620	0.6656	-
0.9066	1630	0.8432	-
0.9121	1640	0.5653	-
0.9177	1650	0.9223	-
0.9232	1660	0.5962	-
0.9288	1670	0.8247	-
0.9344	1680	0.5816	-
0.9399	1690	0.4149	-
0.9455	1700	0.7022	0.7110
0.9511	1710	0.8407	-
0.9566	1720	0.6638	-
0.9622	1730	0.584	-
0.9677	1740	0.4661	-
0.9733	1750	0.8718	-
0.9789	1760	0.9301	-
0.9844	1770	0.6969	-
0.9900	1780	0.6779	-
0.9956	1790	0.5245	-
1.0011	1800	0.6074	0.7736
1.0067	1810	0.6787	-
1.0122	1820	0.7032	-
1.0178	1830	0.52	-
1.0234	1840	0.573	-
1.0289	1850	0.892	-
1.0345	1860	0.7932	-
1.0400	1870	0.5999	-
1.0456	1880	0.5743	-
1.0512	1890	0.7808	-
1.0567	1900	0.6154	0.7187
1.0623	1910	0.4507	-
1.0679	1920	0.7064	-
1.0734	1930	0.7717	-
1.0790	1940	0.6801	-
1.0845	1950	0.5516	-
1.0901	1960	0.5035	-
1.0957	1970	0.5313	-
1.1012	1980	0.8015	-
1.1068	1990	0.4896	-
1.1123	2000	0.6729	0.7362
1.1179	2010	0.4016	-
1.1235	2020	0.5297	-
1.1290	2030	0.7291	-
1.1346	2040	0.6016	-
1.1402	2050	0.7842	-
1.1457	2060	0.9177	-
1.1513	2070	0.8202	-
1.1568	2080	0.5088	-
1.1624	2090	0.5693	-
1.1680	2100	0.5345	0.7454
1.1735	2110	0.7902	-
1.1791	2120	0.6566	-
1.1846	2130	0.8788	-
1.1902	2140	0.5827	-
1.1958	2150	0.637	-
1.2013	2160	0.8633	-
1.2069	2170	0.3402	-
1.2125	2180	0.7573	-
1.2180	2190	0.6678	-
1.2236	2200	0.6598	0.6689
1.2291	2210	0.5696	-
1.2347	2220	0.6602	-
1.2403	2230	0.6607	-
1.2458	2240	0.79	-
1.2514	2250	0.6669	-
1.2570	2260	0.6055	-
1.2625	2270	0.6212	-
1.2681	2280	0.8946	-
1.2736	2290	0.552	-
1.2792	2300	0.7008	0.6983
1.2848	2310	0.4716	-
1.2903	2320	0.5656	-
1.2959	2330	0.8129	-
1.3014	2340	0.4394	-
1.3070	2350	0.701	-
1.3126	2360	0.6499	-
1.3181	2370	0.5047	-
1.3237	2380	0.6408	-
1.3293	2390	0.5313	-
1.3348	2400	0.6719	0.6520
1.3404	2410	0.7874	-
1.3459	2420	0.4832	-
1.3515	2430	0.6547	-
1.3571	2440	0.5849	-
1.3626	2450	0.6484	-
1.3682	2460	0.58	-
1.3737	2470	0.7658	-
1.3793	2480	0.6171	-
1.3849	2490	0.6701	-
1.3904	2500	0.5618	0.6657
1.3960	2510	0.6476	-
1.4016	2520	0.63	-
1.4071	2530	0.572	-
1.4127	2540	0.5754	-
1.4182	2550	0.6653	-
1.4238	2560	0.7646	-
1.4294	2570	0.569	-
1.4349	2580	0.7779	-
1.4405	2590	0.5836	-
1.4461	2600	0.6308	0.6516
1.4516	2610	0.6666	-
1.4572	2620	0.6455	-
1.4627	2630	0.6055	-
1.4683	2640	0.7232	-
1.4739	2650	0.6897	-
1.4794	2660	0.5363	-
1.4850	2670	0.6541	-
1.4905	2680	0.4246	-
1.4961	2690	0.7298	-
1.5017	2700	0.7172	0.6607
1.5072	2710	0.7145	-
1.5128	2720	0.7005	-
1.5184	2730	0.5449	-
1.5239	2740	0.7212	-
1.5295	2750	0.7456	-
1.5350	2760	0.6035	-
1.5406	2770	0.522	-
1.5462	2780	0.6602	-
1.5517	2790	0.6164	-
1.5573	2800	0.4539	0.6169
1.5628	2810	0.5992	-
1.5684	2820	0.6953	-
1.5740	2830	0.5285	-
1.5795	2840	0.5541	-
1.5851	2850	0.7905	-
1.5907	2860	0.7597	-
1.5962	2870	0.6202	-
1.6018	2880	0.7864	-
1.6073	2890	0.4652	-
1.6129	2900	0.5419	0.6443
1.6185	2910	0.4241	-
1.6240	2920	0.6315	-
1.6296	2930	0.5556	-
1.6352	2940	0.5154	-
1.6407	2950	0.6229	-
1.6463	2960	0.5244	-
1.6518	2970	0.431	-
1.6574	2980	0.7253	-
1.6630	2990	0.5751	-
1.6685	3000	0.618	0.6336
1.6741	3010	0.4592	-
1.6796	3020	0.6263	-
1.6852	3030	0.7317	-
1.6908	3040	0.6233	-
1.6963	3050	0.6546	-
1.7019	3060	0.6236	-
1.7075	3070	0.6012	-
1.7130	3080	0.5819	-
1.7186	3090	0.4667	-
1.7241	3100	0.5198	0.6339
1.7297	3110	0.6028	-
1.7353	3120	0.7013	-
1.7408	3130	0.6106	-
1.7464	3140	0.5535	-
1.7519	3150	0.5766	-
1.7575	3160	0.5127	-
1.7631	3170	0.786	-
1.7686	3180	0.5813	-
1.7742	3190	0.3937	-
1.7798	3200	0.5797	0.6450
1.7853	3210	0.47	-
1.7909	3220	0.6528	-
1.7964	3230	0.4784	-
1.8020	3240	0.7885	-
1.8076	3250	0.558	-
1.8131	3260	0.5268	-
1.8187	3270	0.5434	-
1.8242	3280	0.5277	-
1.8298	3290	0.6126	-
1.8354	3300	0.6411	0.6487
1.8409	3310	0.6255	-
1.8465	3320	0.5895	-
1.8521	3330	0.6065	-
1.8576	3340	0.7614	-
1.8632	3350	0.6079	-
1.8687	3360	0.8003	-
1.8743	3370	0.5454	-
1.8799	3380	0.6056	-
1.8854	3390	0.6906	-
1.8910	3400	0.4542	0.6413
1.8966	3410	0.6845	-
1.9021	3420	0.5585	-
1.9077	3430	0.5673	-
1.9132	3440	0.4752	-
1.9188	3450	0.5202	-
1.9244	3460	0.6504	-
1.9299	3470	0.6346	-
1.9355	3480	0.4864	-
1.9410	3490	0.529	-
1.9466	3500	0.583	0.6556
1.9522	3510	0.6182	-
1.9577	3520	0.6825	-
1.9633	3530	0.624	-
1.9689	3540	0.6257	-
1.9744	3550	0.6063	-
1.9800	3560	0.6281	-
1.9855	3570	0.4984	-
1.9911	3580	0.4623	-
1.9967	3590	0.37	-
2.0022	3600	0.5525	0.6623
2.0078	3610	0.6398	-
2.0133	3620	0.5049	-
2.0189	3630	0.3842	-
2.0245	3640	0.376	-
2.0300	3650	0.5997	-
2.0356	3660	0.4695	-
2.0412	3670	0.6691	-
2.0467	3680	0.5538	-
2.0523	3690	0.5726	-
2.0578	3700	0.4352	0.6381
2.0634	3710	0.5047	-
2.0690	3720	0.6121	-
2.0745	3730	0.4385	-
2.0801	3740	0.5293	-
2.0857	3750	0.4501	-
2.0912	3760	0.54	-
2.0968	3770	0.6387	-
2.1023	3780	0.5413	-
2.1079	3790	0.4567	-
2.1135	3800	0.6769	0.6179

• The bold row denotes the saved checkpoint.

Framework Versions

• Python: 3.10.12
• Sentence Transformers: 4.0.2
• Transformers: 4.51.2
• PyTorch: 2.1.0+cu118
• Accelerate: 1.6.0
• Datasets: 3.5.0
• Tokenizers: 0.21.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply},
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}